lucataco/llama-2-13b-chat – Run with an API on Replicate

lucataco / llama-2-13b-chat

Meta's Llama 2 13b Chat - GPTQ

Cold

Public
18.6K runs
L40S
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Prompt to send to Llama v2

Default: "Tell me about AI"

system_prompt

string

Shift + Return to add a new line

You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.

System prompt that helps guide system behavior

Default: "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."

max_new_tokens

integer

(minimum: 1, maximum: 4096)

Number of new tokens

Default: 512

temperature

number

(minimum: 0, maximum: 5)

Randomness of outputs, 0 is deterministic, greater than 1 is random

Default: 0.75

top_p

number

(minimum: 0.01, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 0.95

repetition_penalty

number

(minimum: 0, maximum: 5)

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it

Default: 1.1

Run this model in Node.js with one line of code:

npx create-replicate --model=lucataco/llama-2-13b-chat

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/llama-2-13b-chat:18f253bfce9f33fe67ba4f659232c509fbdfb5025e5dbe6027f72eeb91c8624b",
  {
    input: {
      top_p: 0.95,
      prompt: "Tell me about AI",
      temperature: 0.75,
      system_prompt: "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
      max_new_tokens: 512,
      repetition_penalty: 1.1
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run lucataco/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/llama-2-13b-chat:18f253bfce9f33fe67ba4f659232c509fbdfb5025e5dbe6027f72eeb91c8624b",
    input={
        "top_p": 0.95,
        "prompt": "Tell me about AI",
        "temperature": 0.75,
        "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
        "max_new_tokens": 512,
        "repetition_penalty": 1.1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "lucataco/llama-2-13b-chat:18f253bfce9f33fe67ba4f659232c509fbdfb5025e5dbe6027f72eeb91c8624b",
    "input": {
      "top_p": 0.95,
      "prompt": "Tell me about AI",
      "temperature": 0.75,
      "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don\'t know the answer to a question, please don\'t share false information.",
      "max_new_tokens": 512,
      "repetition_penalty": 1.1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Hello! I'd be happy to help answer your questions about AI. Artificial intelligence (AI) refers to the use of technology to perform tasks that typically require human intelligence, such as learning, problem-solving, and decision-making. There are many different types of AI, including: 1. Machine learning: This is a type of AI that allows computers to learn from data without being explicitly programmed. Machine learning algorithms can be used for tasks such as image and speech recognition, natural language processing, and predictive analytics. 2. Deep learning: This is a type of machine learning that uses neural networks to analyze data. Neural networks are computer systems that are designed to mimic the structure and function of the human brain. 3. Natural language processing (NLP): This is a field of AI that focuses on the interaction between computers and humans using natural language. NLP can be used for tasks such as text analysis, sentiment analysis, and chatbots. 4. Robotics: This is the use of AI to control robots that can perform physical tasks. Robotics can be used in industries such as manufacturing, logistics, and healthcare. 5. Computer vision: This is the use of AI to interpret and understand visual data from the world around us. Computer vision can be used for tasks such as object recognition, facial recognition, and autonomous vehicles. AI has many potential benefits, such as increasing efficiency, improving accuracy, and enhancing decision-making. However, it also raises important ethical and social questions, such as privacy concerns, bias, and job displacement. It's important to note that AI is not a single entity or a replacement for human intelligence, but rather a set of tools and techniques that can augment and enhance human capabilities. AI is already being used in many industries and aspects of our lives, from virtual assistants like Siri and Alexa to self-driving cars and medical diagnosis. If you have any specific questions or concerns about AI, I would be happy to try to help answer them for you.</s>

{
  "completed_at": "2023-07-24T16:20:51.260584Z",
  "created_at": "2023-07-24T16:20:27.274045Z",
  "data_removed": false,
  "error": null,
  "id": "pz7m7ndbe36acybxzpz7bchlcm",
  "input": {
    "top_p": 0.95,
    "prompt": "Tell me about AI",
    "temperature": 0.75,
    "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
    "max_new_tokens": 512,
    "repetition_penalty": 1.1
  },
  "logs": null,
  "metrics": {
    "predict_time": 24.014852,
    "total_time": 23.986539
  },
  "output": "  Hello! I'd be happy to help answer your questions about AI. Artificial intelligence (AI) refers to the use of technology to perform tasks that typically require human intelligence, such as learning, problem-solving, and decision-making. There are many different types of AI, including:\n\n1. Machine learning: This is a type of AI that allows computers to learn from data without being explicitly programmed. Machine learning algorithms can be used for tasks such as image and speech recognition, natural language processing, and predictive analytics.\n2. Deep learning: This is a type of machine learning that uses neural networks to analyze data. Neural networks are computer systems that are designed to mimic the structure and function of the human brain.\n3. Natural language processing (NLP): This is a field of AI that focuses on the interaction between computers and humans using natural language. NLP can be used for tasks such as text analysis, sentiment analysis, and chatbots.\n4. Robotics: This is the use of AI to control robots that can perform physical tasks. Robotics can be used in industries such as manufacturing, logistics, and healthcare.\n5. Computer vision: This is the use of AI to interpret and understand visual data from the world around us. Computer vision can be used for tasks such as object recognition, facial recognition, and autonomous vehicles.\n\nAI has many potential benefits, such as increasing efficiency, improving accuracy, and enhancing decision-making. However, it also raises important ethical and social questions, such as privacy concerns, bias, and job displacement.\n\nIt's important to note that AI is not a single entity or a replacement for human intelligence, but rather a set of tools and techniques that can augment and enhance human capabilities. AI is already being used in many industries and aspects of our lives, from virtual assistants like Siri and Alexa to self-driving cars and medical diagnosis.\n\nIf you have any specific questions or concerns about AI, I would be happy to try to help answer them for you.</s>",
  "started_at": "2023-07-24T16:20:27.245732Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/pz7m7ndbe36acybxzpz7bchlcm",
    "cancel": "https://api.replicate.com/v1/predictions/pz7m7ndbe36acybxzpz7bchlcm/cancel"
  },
  "version": "18f253bfce9f33fe67ba4f659232c509fbdfb5025e5dbe6027f72eeb91c8624b"
}

Generated in

24.0 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.080 to run on Replicate, or 12 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 82 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This an implementation of the model: TheBloke/Llama-2-13b-Chat-GPTQ

A quantized version of the Llama 2 13b chat model

Give me a follow if you like my work! @lucataco93